geney 1.3.71__py2.py3-none-any.whl → 1.3.73__py2.py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of geney might be problematic. Click here for more details.
geney/splicing_utils.py
CHANGED
|
@@ -540,7 +540,12 @@ def process_pairwise_epistasis_explicit(mid, engine='spliceai'):
|
|
|
540
540
|
lower_pos, upper_pos = int(parts[2]), int(parts[6])
|
|
541
541
|
|
|
542
542
|
# Load gene and its transcript (as pre-mRNA)
|
|
543
|
-
g = Gene.from_file(parts[0]).transcript()
|
|
543
|
+
g = Gene.from_file(parts[0]).transcript()
|
|
544
|
+
|
|
545
|
+
if g is not None:
|
|
546
|
+
g.generate_pre_mrna()
|
|
547
|
+
else:
|
|
548
|
+
return pd.DataFrame()
|
|
544
549
|
|
|
545
550
|
# If gene is on the reverse strand, swap positions and set factor to -1.
|
|
546
551
|
if g.rev:
|
|
@@ -597,8 +602,18 @@ def process_pairwise_epistasis_explicit(mid, engine='spliceai'):
|
|
|
597
602
|
).round(2)
|
|
598
603
|
|
|
599
604
|
# Drop columns that do not vary (only one unique value).
|
|
600
|
-
acceptors_df = acceptors_df.loc[:, acceptors_df.nunique() > 1]
|
|
601
|
-
donors_df = donors_df.loc[:, donors_df.nunique() > 1]
|
|
605
|
+
# acceptors_df = acceptors_df.loc[:, acceptors_df.nunique() > 1]
|
|
606
|
+
# donors_df = donors_df.loc[:, donors_df.nunique() > 1]
|
|
607
|
+
if (acceptors_df.nunique() > 1).any():
|
|
608
|
+
acceptors_df = acceptors_df.loc[:, acceptors_df.nunique() > 1]
|
|
609
|
+
else:
|
|
610
|
+
acceptors_df = acceptors_df.iloc[:, [0]]
|
|
611
|
+
|
|
612
|
+
# For donors_df:
|
|
613
|
+
if (donors_df.nunique() > 1).any():
|
|
614
|
+
donors_df = donors_df.loc[:, donors_df.nunique() > 1]
|
|
615
|
+
else:
|
|
616
|
+
donors_df = donors_df.iloc[:, [0]]
|
|
602
617
|
|
|
603
618
|
# Further filter acceptors: keep only columns where the value in the second row is < 0.1.
|
|
604
619
|
# (Assumes that the second row (iloc[1]) represents a specific measure you wish to threshold.)
|
|
@@ -607,13 +622,7 @@ def process_pairwise_epistasis_explicit(mid, engine='spliceai'):
|
|
|
607
622
|
def add_features_and_filter(df):
|
|
608
623
|
if df.shape[1] == 0:
|
|
609
624
|
return df # Nothing to process if no columns remain.
|
|
610
|
-
# Compute the residual:
|
|
611
|
-
# (row 3 - row 0) minus ( (row 1 - row 0) + (row 2 - row 0) )
|
|
612
625
|
df.loc['residual'] = (df.iloc[3] - df.iloc[0]) - ((df.iloc[1] - df.iloc[0]) + (df.iloc[2] - df.iloc[0]))
|
|
613
|
-
# Keep only columns where the absolute residual exceeds 0.1.
|
|
614
|
-
# df = df.loc[:, df.loc['residual'].abs() > 0.1]
|
|
615
|
-
# if df.shape[1] == 0:
|
|
616
|
-
# return df
|
|
617
626
|
# Compute deviations relative to the baseline (row 0)
|
|
618
627
|
df.loc['deviation1'] = df.iloc[1] - df.iloc[0]
|
|
619
628
|
df.loc['deviation2'] = df.iloc[2] - df.iloc[0]
|
|
@@ -631,31 +640,7 @@ def process_pairwise_epistasis_explicit(mid, engine='spliceai'):
|
|
|
631
640
|
acceptors_df.loc['site_type', :] = 1
|
|
632
641
|
|
|
633
642
|
df = pd.concat([acceptors_df, donors_df], axis=1)
|
|
634
|
-
|
|
635
|
-
# if df.shape[1] == 0:
|
|
636
|
-
# return df
|
|
637
|
-
#
|
|
638
|
-
# mask = df.apply(
|
|
639
|
-
# lambda col: (
|
|
640
|
-
# (abs(col['residual']) > 0.1) and
|
|
641
|
-
# (abs(col['deviation1'] + col['deviation2']) < 0.1)
|
|
642
|
-
# ),
|
|
643
|
-
# axis=0
|
|
644
|
-
# )
|
|
645
|
-
#
|
|
646
|
-
# df.loc['synergistic'] = 0
|
|
647
|
-
# df.loc['synergistic', mask] = 1
|
|
648
|
-
#
|
|
649
|
-
# mask = df.apply(
|
|
650
|
-
# lambda col: (
|
|
651
|
-
# (abs(col['residual']) > 0.1) and
|
|
652
|
-
# (abs(col['total_deviation']) <= 0.25)
|
|
653
|
-
# ),
|
|
654
|
-
# axis=0
|
|
655
|
-
# )
|
|
656
|
-
#
|
|
657
|
-
# df.loc['antagonistic'] = 0
|
|
658
|
-
# df.loc['antagonistic', mask] = 1
|
|
643
|
+
|
|
659
644
|
df.loc['mut_id'] = mid
|
|
660
645
|
df.loc['engine'] = engine
|
|
661
646
|
df.loc['site'] = df.columns
|
|
@@ -16,7 +16,7 @@ geney/pangolin_utils.py,sha256=9jdBXlOcRaUdfi-UpUxHA0AkTMZkUF-Lt7HVZ1nEm3s,2973
|
|
|
16
16
|
geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
|
|
17
17
|
geney/seqmat_utils.py,sha256=wzb3PX5it5bpIFQvcxyzlxfhoJTbHHbsjg0rzh05iVs,19753
|
|
18
18
|
geney/spliceai_utils.py,sha256=tVY0T6F6l3fNoaktpn7Kq0oH5ZM0ThFYt9nPi_lfakw,3077
|
|
19
|
-
geney/splicing_utils.py,sha256
|
|
19
|
+
geney/splicing_utils.py,sha256=mAiZXBzb0IzZ_O0CIhxR36q8H9xqPXJOUk2fU1UTqc8,47313
|
|
20
20
|
geney/survival_utils.py,sha256=KnAzEviMuXh6SnVXId9PgsFLSbgkduTvYoIthxN7FPA,6886
|
|
21
21
|
geney/tcga_utils.py,sha256=D_BNHm-D_K408dlcJm3hzH2c6QNFjQsKvUcOPiQRk7g,17612
|
|
22
22
|
geney/tis_utils.py,sha256=la0CZroaKe5RgAyFd4Bf_DqQncklWgAY2823xVst98o,7813
|
|
@@ -25,7 +25,7 @@ geney/translation_initiation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NM
|
|
|
25
25
|
geney/translation_initiation/tis_utils.py,sha256=AF3siFjuQH-Rs44EV-80zHdbxRMvN4woLFSHroWIETc,4448
|
|
26
26
|
geney/translation_initiation/resources/kozak_pssm.json,sha256=pcd0Olziutq-6H3mFWDCD9cujQ_AlZO-iiOvBl82hqE,1165
|
|
27
27
|
geney/translation_initiation/resources/tis_regressor_model.joblib,sha256=IXb4DUDhJ5rBDKcqMk9zE3ECTZZcdj7Jixz3KpoZ7OA,2592025
|
|
28
|
-
geney-1.3.
|
|
29
|
-
geney-1.3.
|
|
30
|
-
geney-1.3.
|
|
31
|
-
geney-1.3.
|
|
28
|
+
geney-1.3.73.dist-info/METADATA,sha256=zBDPXEkIQIf58meB91wGEvGGPfe1rlR7-XZX9toMKdM,990
|
|
29
|
+
geney-1.3.73.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
|
|
30
|
+
geney-1.3.73.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
|
|
31
|
+
geney-1.3.73.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|